© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21984
    Prev
    Next
    INDEX
    Explanations

    asking about possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įä¸Ģå®ļ
    -0.15
    å¾Īå¤ļ
    -0.12
    ä¸įå°ij人
    -0.12
    å¾Īå¤ļäºĭæĥħ
    -0.12
    å¾Īå¤ļ人
    -0.11
    æľªå¿ħ
    -0.11
    ä¸įè§ģ
    -0.11
    ä¸įå°ij
    -0.10
     многиÑħ
    -0.10
    许å¤ļ
    -0.10
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.19
     ever
    0.13
    /how
    0.13
    羣çļĦ
    0.13
     вообÑīе
    0.13
    è¿ĺæľīä»Ģä¹Ī
    0.12
     realmente
    0.12
     really
    0.12
     EVER
    0.12
     há»ģ
    0.12
    Activations Density 0.141%

    No Known Activations